Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    negative signs in mathematical expressions or formulas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mathematical subtraction and set difference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     препратки
    -0.68
     BoxFit
    -0.65
     estekak
    -0.63
    webElementXpaths
    -0.59
     المعيارى
    -0.58
    ViewFeatures
    -0.56
    protoimpl
    -0.55
    Datuak
    -0.55
     للمعارف
    -0.54
    tagHelper
    -0.54
    POSITIVE LOGITS
    setminus
    0.63
    ∖
    0.59
    }-\
    0.58
    subtract
    0.58
    >−</
    0.57
     subtract
    0.56
    Subtract
    0.55
    }}-\
    0.54
    }-
    0.51
    backslash
    0.51
    Act Density 0.593%

    No Known Activations